signals-scout-data-pipelines
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from pipeline logs, error messages, and recipient-level outcomes which could contain attacker-controlled content designed to influence the agent's behavior.
- Ingestion points: The skill reads external data via the tools
cdp-functions-logs-retrieve,workflows-list-invocations, andworkflows-logsas described in SKILL.md. - Boundary markers: Present; the skill includes a dedicated section titled "Untrusted data — logs, errors, and payload echoes" that explicitly instructs the agent to treat these inputs as data only and never as instructions.
- Capability inventory: The agent has the capability to write reports to an inbox via
scout-emit-reportandscout-edit-report, and to store persistent findings in a scratchpad viascout-scratchpad-remember(SKILL.md). - Sanitization: Present; the instructions require the agent to truncate long messages and strip payload echoes from any findings before they are reported.
Audit Metadata